Weijia Shi

Artificial Intelligence · International Conference on Learning Representations · 2019–2023

A researcher in the Science corpus: 9 papers; trusts 314 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 340 citations into it; #34,612 of 35,345 by trust here, #4,602 by citations
• Computer Vision and Pattern Recognition — 160 citations into it
• Natural Language Processing — 147 citations into it
• Large Language Models — 92 citations into it
• Evaluation & Benchmarks — 78 citations into it
• Multimodal Learning — 62 citations into it
• Information Retrieval & Search — 38 citations into it
• Representation & Self-Supervised Learning — 33 citations into it

Whom Weijia Shi trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Ilya Sutskever
6. Kaiming He
7. Yann LeCun
8. Chin-Yew Lin
9. Jimmy Ba
10. Alex Graves

Who trusts Weijia Shi overall

1. Rongwu Xu
2. Shitao Xiao
3. Sewon Min
4. A. Chevalier
5. Ruiqi Zhang
6. Zach Nussbaum
7. Yung-Sung Chuang
8. Jian Xie
9. Soyeong Jeong
10. Shuo Yang

Papers from Weijia Shi's perspective

Ordered by how strongly the researchers Weijia Shi trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. Attention is All you Need (Neural Information Processing Systems)
3. ImageNet classification with deep convolutional neural networks
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
7. ImageNet: A large-scale hierarchical image database
8. Gradient-based learning applied to document recognition
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• REPLUG: Retrieval-Augmented Black-Box Language Models (2023) — 1,051 citations
• Retrieval-Augmented Multimodal Language Modeling (2023) — 166 citations
• Examining Gender Bias in Languages with Grammatical Gender (2019) — 115 citations
• Selective Annotation Makes Language Models Better Few-Shot Learners (2022) — 329 citations
• One Embedder, Any Task: Instruction-Finetuned Text Embeddings (2022) — 475 citations
• Fine-Grained Human Feedback Gives Better Rewards for Language Model Training (2023) — 481 citations
• Detecting Pretraining Data from Large Language Models (2023) — 424 citations
• Trusting Your Evidence: Hallucinate Less with Context-aware Decoding (2023) — 387 citations
• PromptCap: Prompt-Guided Task-Aware Image Captioning (2022) — 142 citations